{"id":"https://openalex.org/W2913303417","doi":"https://doi.org/10.1021/acs.jcim.8b00977","title":"Feature Engineering for Materials Chemistry\u2014Does Size Matter?","display_name":"Feature Engineering for Materials Chemistry\u2014Does Size Matter?","publication_year":2019,"publication_date":"2019-02-07","ids":{"openalex":"https://openalex.org/W2913303417","doi":"https://doi.org/10.1021/acs.jcim.8b00977","mag":"2913303417","pmid":"https://pubmed.ncbi.nlm.nih.gov/30730732"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.8b00977","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.8b00977","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021556977","display_name":"Roger D. Amos","orcid":"https://orcid.org/0000-0003-2868-7994"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roger D. Amos","raw_affiliation_strings":["ANU Supercomputer Facility, Leonard Huxley Building 56, Mills Road, Canberra, ACT 2601, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ANU Supercomputer Facility, Leonard Huxley Building 56, Mills Road, Canberra, ACT 2601, Australia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036058579","display_name":"Rika Kobayashi","orcid":"https://orcid.org/0000-0002-0672-833X"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rika Kobayashi","raw_affiliation_strings":["ANU Supercomputer Facility, Leonard Huxley Building 56, Mills Road, Canberra, ACT 2601, Australia","International Centre for Quantum and Molecular Structure, College of Sciences, Shanghai University, Shanghai 200444, China"],"raw_orcid":"https://orcid.org/0000-0002-0672-833X","affiliations":[{"raw_affiliation_string":"ANU Supercomputer Facility, Leonard Huxley Building 56, Mills Road, Canberra, ACT 2601, Australia","institution_ids":[]},{"raw_affiliation_string":"International Centre for Quantum and Molecular Structure, College of Sciences, Shanghai University, Shanghai 200444, China","institution_ids":["https://openalex.org/I113940042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036058579"],"corresponding_institution_ids":["https://openalex.org/I113940042"],"apc_list":null,"apc_paid":null,"fwci":0.3672,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.52231524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"59","issue":"5","first_page":"1873","last_page":"1881"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12613","display_name":"X-ray Diffraction in Crystallography","score":0.9229999780654907,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.7659482955932617},{"id":"https://openalex.org/keywords/band-gap","display_name":"Band gap","score":0.6210591793060303},{"id":"https://openalex.org/keywords/root-mean-square","display_name":"Root mean square","score":0.5963984727859497},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5878989696502686},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5839398503303528},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5540195107460022},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5264359712600708},{"id":"https://openalex.org/keywords/approximation-error","display_name":"Approximation error","score":0.511214017868042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.39124763011932373},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.38711321353912354},{"id":"https://openalex.org/keywords/biological-system","display_name":"Biological system","score":0.38568735122680664},{"id":"https://openalex.org/keywords/computational-physics","display_name":"Computational physics","score":0.37618395686149597},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35170435905456543},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.31713706254959106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2742547392845154},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.27355337142944336},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.2504805028438568},{"id":"https://openalex.org/keywords/optoelectronics","display_name":"Optoelectronics","score":0.17271554470062256}],"concepts":[{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.7659482955932617},{"id":"https://openalex.org/C181966813","wikidata":"https://www.wikidata.org/wiki/Q806352","display_name":"Band gap","level":2,"score":0.6210591793060303},{"id":"https://openalex.org/C71907059","wikidata":"https://www.wikidata.org/wiki/Q223323","display_name":"Root mean square","level":2,"score":0.5963984727859497},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5878989696502686},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5839398503303528},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5540195107460022},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5264359712600708},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.511214017868042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39124763011932373},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.38711321353912354},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.38568735122680664},{"id":"https://openalex.org/C30475298","wikidata":"https://www.wikidata.org/wiki/Q909554","display_name":"Computational physics","level":1,"score":0.37618395686149597},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35170435905456543},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31713706254959106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2742547392845154},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.27355337142944336},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2504805028438568},{"id":"https://openalex.org/C49040817","wikidata":"https://www.wikidata.org/wiki/Q193091","display_name":"Optoelectronics","level":1,"score":0.17271554470062256},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077318","descriptor_name":"Density Functional Theory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077318","descriptor_name":"Density Functional Theory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077318","descriptor_name":"Density Functional Theory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008027","descriptor_name":"Light","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008027","descriptor_name":"Light","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008027","descriptor_name":"Light","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010316","descriptor_name":"Particle Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010316","descriptor_name":"Particle Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010316","descriptor_name":"Particle Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012834","descriptor_name":"Silver","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012834","descriptor_name":"Silver","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012834","descriptor_name":"Silver","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D053768","descriptor_name":"Metal Nanoparticles","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D053768","descriptor_name":"Metal Nanoparticles","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D053768","descriptor_name":"Metal Nanoparticles","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.8b00977","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.8b00977","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:30730732","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30730732","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320325553","display_name":"Shanghai University","ror":"https://ror.org/006teas31"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W85970651","https://openalex.org/W1520127302","https://openalex.org/W1531674615","https://openalex.org/W1678356000","https://openalex.org/W1800437104","https://openalex.org/W1952152691","https://openalex.org/W1981368803","https://openalex.org/W1992676052","https://openalex.org/W1992985800","https://openalex.org/W1994880295","https://openalex.org/W2011327487","https://openalex.org/W2017805851","https://openalex.org/W2022696619","https://openalex.org/W2025111634","https://openalex.org/W2027123487","https://openalex.org/W2029413789","https://openalex.org/W2033206800","https://openalex.org/W2077566309","https://openalex.org/W2084972556","https://openalex.org/W2088283179","https://openalex.org/W2088331368","https://openalex.org/W2101234009","https://openalex.org/W2104489082","https://openalex.org/W2111732445","https://openalex.org/W2115526823","https://openalex.org/W2123750383","https://openalex.org/W2156043887","https://openalex.org/W2162653998","https://openalex.org/W2464725281","https://openalex.org/W2490901606","https://openalex.org/W2509907061","https://openalex.org/W2563751252","https://openalex.org/W2734520197","https://openalex.org/W2743321689","https://openalex.org/W2756682189","https://openalex.org/W2780173879","https://openalex.org/W2790960441","https://openalex.org/W2804431384","https://openalex.org/W2885995996","https://openalex.org/W2911964244","https://openalex.org/W2919386454","https://openalex.org/W2962872055","https://openalex.org/W3100710928","https://openalex.org/W3101744125","https://openalex.org/W3102449990","https://openalex.org/W6891662443"],"related_works":["https://openalex.org/W2102148524","https://openalex.org/W4387072315","https://openalex.org/W3011201302","https://openalex.org/W2180861079","https://openalex.org/W135180227","https://openalex.org/W2728376045","https://openalex.org/W2350552870","https://openalex.org/W3005025283","https://openalex.org/W2659933339","https://openalex.org/W2742825757"],"abstract_inverted_index":{"The":[0,75],"effects":[1,47],"of":[2,8,55,72,85,104,121,128,135,143,146,154,162,169],"structural":[3,39],"featurizers":[4],"in":[5,68,78,95,109,117],"the":[6,56,69,101,105,110,132,141,155],"prediction":[7,142],"band":[9,32,86,102,149],"gaps":[10,87,103,150],"have":[11],"been":[12],"investigated":[13],"through":[14],"machine":[15],"learning":[16],"by":[17],"application":[18],"to":[19,83,140],"a":[20,52,96,118,144,159],"silver":[21],"nanoparticle":[22],"data":[23,111],"set":[24,112,145],"and":[25,48,124,165],"2254":[26,106],"potential":[27],"light-harvesting":[28,107],"materials":[29,108],"with":[30,38,113],"known":[31],"gaps.":[33],"Elemental":[34],"properties":[35],"were":[36,152],"extended":[37,57],"features":[40],"via":[41],"Voronoi":[42],"polyhedra,":[43],"allowing":[44],"for":[45],"neighbor":[46],"thus":[49],"presumably":[50],"giving":[51,158],"better":[53],"representation":[54],"system.":[58],"However,":[59],"we":[60],"did":[61],"not":[62],"find":[63],"any":[64],"noticeably":[65],"significant":[66],"difference":[67],"predictive":[70],"performance":[71,134],"our":[73,79,136],"model.":[74],"biggest":[76],"improvement":[77],"model":[80,97,137],"was":[81,138],"due":[82],"inclusion":[84],"calculated":[88],"using":[89],"density":[90],"functional":[91],"theory.":[92],"This":[93],"resulted":[94],"that":[98,151],"could":[99],"predict":[100],"an":[114],"accuracy":[115],"reflected":[116],"root-mean-square":[119,160],"error":[120,127,161,168],"0.232":[122],"eV":[123,164],"mean":[125,166],"absolute":[126,167],"0.142":[129],"eV.":[130,171],"Furthermore,":[131],"good":[133],"transferable":[139],"72":[147],"experimental":[148],"independent":[153],"training":[156],"set,":[157],"0.91":[163],"0.76":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}